# google-deepmind/neural-processes

This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

Repository: https://github.com/google-deepmind/neural-processes
Canonical: https://ross.abutalabs.com/products/neural-processes
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2021-01-19T10:04:39+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2906, "days_push": 2052, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1023, forks 154 (observed 2026-08-28T04:03:16.269077+00:00)

## What it is
A collection of Jupyter notebook implementations of the Neural Process family from DeepMind: Conditional Neural Processes (CNPs), Neural Processes (NPs), and Attentive Neural Processes (ANPs). The notebooks explain the model building blocks and can be run in the browser via Colab or locally with Jupyter and TensorFlow.

## Use cases
- learn how conditional neural processes work
- implement neural processes in tensorflow
- understand attentive neural processes
- run neural process demos in colab
- study meta-learning regression models
- reproduce results from the CNP NP and ANP papers

## When to choose
- you want readable, educational notebook implementations of the neural process family
- you want to run the models quickly without setup using Colab
- you are studying the original CNP, NP, and ANP papers and want reference code

## When to avoid
- you need a production-ready or maintained neural process library
- you need modern TensorFlow 2 or PyTorch support
- you need features beyond the three original variants

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, data-visualization
- domain: machine-learning, deep-learning, tutorials
- platform: python, cross-platform
- tags: neural-processes, jupyter-notebooks, tensorflow, regression, probabilistic-models, colab, web-server

## Member repositories
- google-deepmind/neural-processes (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:16.269077+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:08:37.986687+00:00, confidence not recorded.
  - readme: https://github.com/google-deepmind/neural-processes (fetched 2026-08-28T04:03:16.269077+00:00, sha f734dbd06f00)
- Data as of 2026-08-30T08:39:29.467469+00:00.